ABSTRACT
We present a genome polymorphisms/machine learning approach for severe COVID-19 prognosis. Ninety-six Brazilian severe COVID-19 patients and controls were genotyped for 296 innate immunity loci. Our model used a feature selection algorithm, namely recursive feature elimination coupled with a support vector machine, to find the optimal loci classification subset, followed by a support vector machine with the linear kernel (SVM-LK) to classify patients into the severe COVID-19 group. The best features that were selected by the SVM-RFE method included 12 SNPs in 12 genes: PD-L1, PD-L2, IL10RA, JAK2, STAT1, IFIT1, IFIH1, DC-SIGNR, IFNB1, IRAK4, IRF1, and IL10. During the COVID-19 prognosis step by SVM-LK, the metrics were: 85% accuracy, 80% sensitivity, and 90% specificity. In comparison, univariate analysis under the 12 selected SNPs showed some highlights for individual variant alleles that represented risk (PD-L1 and IFIT1) or protection (JAK2 and IFIH1). Variant genotypes carrying risk effects were represented by PD-L2 and IFIT1 genes. The proposed complex classification method can be used to identify individuals who are at a high risk of developing severe COVID-19 outcomes even in uninfected conditions, which is a disruptive concept in COVID-19 prognosis. Our results suggest that the genetic context is an important factor in the development of severe COVID-19.
Subject(s)
COVID-19 , Genome, Human , Humans , B7-H1 Antigen , Interferon-Induced Helicase, IFIH1 , Brazil/epidemiology , COVID-19/diagnosis , COVID-19/genetics , Artificial Intelligence , Algorithms , GenomicsABSTRACT
OBJECTIVES: We assessed the prevalence of SARS-CoV-2 infection, personal protective equipment (PPE) shortages and occurrence of biological accidents among front-line healthcare workers (HCW). DESIGN, SETTING AND PARTICIPANTS: Using respondent-driven sampling, the study recruited distinct categories of HCW attending suspected or confirmed patients with COVID-19 from May 2020 to February 2021, in the Recife metropolitan area, Northeast Brazil. OUTCOME MEASURES: The criterion to assess SARS-CoV-2 infection among HCW was a positive self-reported PCR test. RESULTS: We analysed 1525 HCW: 527 physicians, 471 registered nurses, 263 nursing assistants and 264 physical therapists. Women predominated in all categories (81.1%; 95% CI: 77.8% to 84.1%). Nurses were older with more comorbidities (hypertension and overweight/obesity) than the other staff. The overall prevalence of SARS-CoV-2 infection was 61.8% (95% CI: 55.7% to 67.5%) after adjustment for the cluster random effect, weighted by network, and the reference population size. Risk factors for a positive RT-PCR test were being a nursing assistant (OR adjusted: 2.56; 95% CI: 1.42 to 4.61), not always using all recommended PPE while assisting patients with COVID-19 (OR adj: 2.15; 95% CI: 1.02 to 4.53) and reporting a splash of biological fluid/respiratory secretion in the eyes (OR adj: 3.37; 95% CI: 1.10 to 10.34). CONCLUSIONS: This study shows the high frequency of SARS-CoV2 infection among HCW presumably due to workplace exposures. In our setting, nursing assistant comprised the most vulnerable category. Our findings highlight the need for improving healthcare facility environments, specific training and supervision to cope with public health emergencies.